{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:19:37Z","timestamp":1778048377841,"version":"3.51.4"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00195","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1959-1968","source":"Crossref","is-referenced-by-count":0,"title":["Seeing is Believing (and Predicting): Context-Aware Multi-Human Behavior Prediction with Vision Language Models"],"prefix":"10.1109","author":[{"given":"Utsav","family":"Panchal","sequence":"first","affiliation":[{"name":"University of Stuttgart,Institute of Architecture of Application Systems,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Stuttgart,Institute of Architecture of Application Systems,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luigi","family":"Palmieri","sequence":"additional","affiliation":[{"name":"Bosch Research,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ilche","family":"Georgievski","sequence":"additional","affiliation":[{"name":"University of Stuttgart,Institute of Architecture of Application Systems,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Aiello","sequence":"additional","affiliation":[{"name":"University of Stuttgart,Institute of Architecture of Application Systems,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00560"},{"key":"ref2","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2025.3552345"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00576"},{"key":"ref5","article-title":"On the efficacy of text-based input modalities for action anticipation","author":"Beedu","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.390"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3627546\/mm1"},{"key":"ref8","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proc. of the European Conf. on computer vision (ECCV)","author":"Damen"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3685520"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/UEMCON47517.2019.8993060"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3482169"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611090"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00237"},{"issue":"2","key":"ref17","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_46"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_9"},{"key":"ref20","article-title":"Understanding the effects of rlhf on llm generalisation and diversity","author":"Kirk","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01594-9"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref24","article-title":"Human action anticipation: A survey","author":"Lai","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3051319"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3280816"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127838"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN63969.2025.11217803"},{"key":"ref30","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref31","article-title":"Unveiling the secret recipe: A guide for supervised fine-tuning small llms","author":"Pareja","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s13278-016-0379-0"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00886"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"key":"ref35","first-page":"23","article-title":"Sayplan: Grounding large language models using 3d scene graphs for scalable robot task planning","volume-title":"Conference on Robot Learning","author":"Rana"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00088"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920917446"},{"key":"ref38","first-page":"27","article-title":"Two-stream convolutional networks for action recognition in videos","author":"Simonyan","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3461552"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493482"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00036"},{"key":"ref42","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref44","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref45","article-title":"Himemformer: Hierarchical memory-aware transformer for multi-agent action anticipation","author":"Wang","year":"2024"},{"key":"ref46","volume-title":"Long-term action anticipation on ego4d","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3281393"},{"key":"ref48","article-title":"Antgpt: Can large language models help long-term action anticipation from videos","author":"Zhao","year":"2024","journal-title":"ICLR"},{"key":"ref49","article-title":"A survey on deep learning techniques for action anticipation","author":"Zhong","year":"2023"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492419.pdf?arnumber=11492419","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:56:25Z","timestamp":1778046985000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492419\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00195","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}